Borrowing it
Nothing to install: this file belongs to genomoncology/biomcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/genomoncology/biomcp/main/AGENTS.mdgit clone --depth 1 https://github.com/genomoncology/biomcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/genomoncology/biomcp/agents-md)<a href="https://agentmods.dev/instructions/genomoncology/biomcp/agents-md"><img src="https://agentmods.dev/badge/instructions/genomoncology/biomcp/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/genomoncology/biomcp/agents-md"><img src="https://agentmods.dev/badge/instructions/genomoncology/biomcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.02114 | $0.02114 |
| Opus 5.5 | $0.00846 | $0.00846 |
| Sonnet 5.5 | $0.00423 | $0.00423 |
| Haiku 4.5 | $0.00211 | $0.00211 |
Grade A, and why
biomcp AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — BioMCP
This repository is public and talks only about itself.
BioMCP is a Rust CLI and MCP server with a Python docs/contract harness. The
Rust runtime lives under src/; Python tests, docs checks, and executable
contracts exercise the shipped CLI/MCP surface.
Packaged agent guide
BioMCP is a biomedical CLI and MCP server. For example, search from the CLI
with biomcp search articles --gene BRAF.
The executable embeds the agent guide and worked examples. Read the guide with
biomcp skill, render the complete guide with biomcp skill render, or install
local copies into your agent directory with biomcp skill install <dir>.
Use biomcp skill list to choose a worked example.
Read the documentation at https://biomcp.org/, including getting started, how-to guides, the user guide and the reference.
Repository contract shape
-
Behavioral contracts are mustmatch executable docs at:
spec/*.mdRun them with
make spec. The spec gates use the standalonemustmatch testbinary throughscripts/run-specs.sh. Cargo artifact preparation and fixture standup belong in the runner andscripts/prepare-spec-artifacts.py, not in ad hoc docs. Specification pages execute prepared paths and must not invokecargo run,cargo build,cargo rustc,cargo test,cargo tree, orcargo metadata. -
Unit/static layers run with
make test: Rust nextest finishes before the Python CLI/MCP/docs contract lane starts, even withmake -j.
Working
Run affected tests on the configured build machine, leaving CARGO_INCREMENTAL unset so the configured compiler cache can run:
cargo nextest run --no-default-features -E 'test(...)'
The routine build job books 8 GiB disk and 7 GiB memory. The Makefile's TEST_LANE_WORKERS sets the shared Cargo, nextest and pytest worker allowance for that booking. Keep the allowance and booking together when measuring a different job shape. Run make test TEST_LANE_WORKERS=1 for a smaller worker allowance.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago Changed · +8 lines · +196 tokens per session caf28eb30121
- 7d ago Changed · +7 lines · +243 tokens per session bc0ed889a482
- 8d ago Changed · +4 lines · +148 tokens per session 776dfcca3140
- 9d ago Changed · -18 tokens per session 049018e6f48d
- 10d ago Changed · +17 lines · +337 tokens per session 089bbb517ced
- 13d ago Changed · -45 tokens per session 5aeca8f668f3
- 14d ago Changed · +2 lines · +27 tokens per session 8a6554c528b3
- 15d ago Changed · -20 lines · +21 tokens per session cd26e96bd119
- 26d ago Changed · +2 lines · +41 tokens per session 46ab8383f47e
- 28d ago First seen · 114 lines · 1,164 tokens per session scan A ce4b1ecd156d
biomcp AGENTS.md is an instructions file published in the GitHub repository genomoncology/biomcp (667 stars, last pushed 4d ago), licensed MIT. It adds 2,114 tokens to every session, about $0.0085 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.